Now, we already know how Joe Biden is close to winning Election 2020 in America. But let’s look back on the forecasts given us from several AI systems before the election got started.
Most of these systems look at data from social media and then use sentiment analysis – which categorizes the emotions expressed in a text – to figure out whether a particular post is in favor or against a certain candidate. The systems then try to find a correlation between the quantity and quality of these expressions and voting patterns. So let’s take a look at what was predicted:
- A system designed by a company called KCore Analytics forecasted that Biden will win the popular vote handily, but that his Electoral College margin will be razor-thin.
- The Italian-based AI company Expert.AI saw Biden in the lead, but only by a few percentage points—a much smaller margin than the seven-point lead Biden has in an average of national polls.
- Polly Pollster, an AI system created by Advanced Symbolics, predicted that Biden will win easily, with Trump having only about an 8% chance of pulling off an upset.
We have to mention that these AI systems work in different ways. For instance, Expert.ai uses a form of AI, based on encoding human expertise in a knowledge graph, to generate its sentiment analysis. The graph is able to identify named entities – such as people, companies, and places – better than many neural network-based approaches can, and it can better understand complex relationships between words than some large statistical language models.
Another important factor that needs taking into account is guarding against bots because as KCore’s Herman Makse told The Independent, fewer of Trump’s likely voters than Biden supporters are on Twitter. That means tweets from Trump supporters are weighted more heavily in social media-based election forecasting models, so there’s a risk that pro-Trump bots could make Trump’s chances appear better than they are in fact.
Let’s sum up what has been written, the main conclusion we are coming to is that all 3 mentioned AI systems were in their forecasts even more accurate than national polls’ data. That is another proof of AI utility and its accuracy in prediction.
Image credit: GPA Photo Archive, https://flic.kr/p/BrRNcA; CC BY-NC 2.0, https://creativecommons.org/licenses/by-nc/2.0/